Talking photo avatar model from Veed
# Subtitles ## Overview Burns subtitles into a video, transcribing automatically or from a supplied SRT. Most social video should ship captioned. ## Model Metadata - Provider: fal - Category: video - Output Type: video - Slug: veed-subtitles ## Notes Use the Playground tab above to test prompts and parameters.
Model input reference derived from preset schema.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| preset | select | Yes | null | Each style defines fonts, colors, layout, and animation. Two tiers with different pricing: - Dynamic presets (2x multiplier): glass, whisper, glide2, fusion, glide, terminal, handwritten. Richer, context-aware rendering that adapts to the input. - Basic presets (1x multiplier): simple, plain, beans, corpo, boo, shadeplay, casper, capri, lowkey, vinta, diego, ali, slay, kitty, hustle, karl, sprout, flex, mint, rizz, vegas. Fixed, lightweight styling with predictable output. |
| language | select | No | null | Improves transcription accuracy, and should match the source audio (not output subtitles). |
| video_url | video | Yes | null | Upload or paste a URL to the video you want to subtitle. |
| srt_content | string | No | null | Paste raw SRT subtitle text. Alternative to srt_file_url. When provided, transcription is skipped. |
| srt_file_url | image | No | null | Upload or paste a URL to your .srt subtitles file. When provided, transcription is skipped. |
| customization | string | No | null | Optional preset overrides: vertical position, shadow intensity, and per-tier text styling (font, weight, hex colour) for each word-importance tier. Any omitted field keeps the preset's default. |